fix: MultilingualEmbedder respects HF_HUB_OFFLINE env var instead of hardcoded local_files_only=True; start.sh uses set -e for error visibility

fix Dockerfile: build indexes on first startup (no network during Docker build)

fix Dockerfile: create src dir before pip install to avoid setuptools egg_base error

add HF Space YAML frontmatter to README (fix CONFIG_ERROR)

regenerate submission.csv with updated metadata

fix email typo, update team info with actual names

fix sandbox link to correct HF username

Fix: role-type skill detection, OpenRouter base_url support, Dockerfile for HF Spaces with 500-profile sample indexes

Remove team information from submission_metadata.yaml

chore: ignore all markdown files except README.md

feat: align candidate relevance ranking & implement robust Turbo Mode fallback

Fix remote candidate search returning 0 results by mapping preferred_work_mode

fix: app.py scoping error + new Sage+Terracotta theme

feat: complete UI redesign with pastel purple/orange theme

feat: interactive mode with API key prompt, improved README

feat: interactive mode with full agentic pipeline, improved batch queries

refactor: extract shared query parser module, clean up imports

fix: reranker degradation, skip_reranker bug, eval latency, branch cleanup

feat: full 100k index pipeline - switch from samples to full offset index

UI: zero gradients, peaceful warm palette, borders for elevation

UI redesign: pastel theme, premium card design, progressive loading

enhanced turbo parser: multi-word skill detection, alias expansion, proper skill extraction

feat: final smoke-test fixes + spectacular README + UI bugfixes

style(style): resolve ruff formatting check warnings

perf(agents): parallelize candidate profile loading

perf(core): reuse open file handle in ProfileStore for fast candidate fetches

perf(search): use np.argpartition for fast top-k selection in BM25

perf(search): upgrade FAISS index to IndexHNSWFlat

feat(data): remove generate_data.py script

style(search): format reranker.py to fix E501 line length issue

style(language): format translator.py to fix E501 line length issues

test(tests): fix str to enum type errors in test suites

feat(search): add --profiles option to build_indexes.py

chore(core): enable listwise ranking by default

feat(data): implement candidate profile generation script

feat(ui): wire search filters from Gradio UI to the orchestrator

feat(language): add HingBERT token classification pipeline for Hinglish NER

feat(language): add MBart-50 translation fallback model

fix(search): implement eager non-blocking reranker model loading and online download fallback

fix(api): wire slider_weights, filters, max_results and remove dead code

fix(core): add default values to MatchScores and slider_weights to SearchRequest

fix(matching): map cultural_fit to semantic_similarity

fix(ranking): remove sync rank and sync _judge_group wrapper

fix(agents): instantiate experience/location models in planner fallback

fix(search): change FAISS index type annotation to faiss.Index

fix(core): wrap OpenAI api_key in SecretStr

fix(agents): compile graph on init and add state filter wiring

chore: fix all ruff lint errors (174 -> 0), clean up unused imports/vars, fix line lengths

Merge PR #1: Overhaul - Plackett-Luce ranking, PII anonymizer, live fairness dashboard, and 40+ bug fixes

Refine skill matching and add original query pipeline